auto-patch README.md

README.md

@@ -38,10 +38,13 @@ more details, including on how to concatenate multi-part files.
 | [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q3_K_S.gguf) | Q3_K_S | 14.2 |  |
 | [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q3_K_M.gguf) | Q3_K_M | 15.7 | lower quality |
 | [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q3_K_L.gguf) | Q3_K_L | 17.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.IQ4_XS.gguf) | IQ4_XS | 17.6 |  |
 | [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q4_K_S.gguf) | Q4_K_S | 18.5 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q4_K_M.gguf) | Q4_K_M | 19.6 | fast, recommended |
 | [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q5_K_S.gguf) | Q5_K_S | 22.3 |  |
 | [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q5_K_M.gguf) | Q5_K_M | 23.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q6_K.gguf) | Q6_K | 26.5 | very good quality |
+| [GGUF](https://huggingface.co/mradermacher/OLMo-2-Instruct-Math-32B-GGUF/resolve/main/OLMo-2-Instruct-Math-32B.Q8_0.gguf) | Q8_0 | 34.4 | fast, best quality |
 
 Here is a handy graph by ikawrakow comparing some lower-quality quant
 types (lower is better):